Text Generation
Transformers
Chinese
English
omni
multimodal
text-to-speech
audio-to-audio
image-to-text
minimind
Instructions to use jingyaogong/minimind-3o-pytorch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jingyaogong/minimind-3o-pytorch with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jingyaogong/minimind-3o-pytorch")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jingyaogong/minimind-3o-pytorch", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use jingyaogong/minimind-3o-pytorch with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jingyaogong/minimind-3o-pytorch" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jingyaogong/minimind-3o-pytorch", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jingyaogong/minimind-3o-pytorch
- SGLang
How to use jingyaogong/minimind-3o-pytorch with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "jingyaogong/minimind-3o-pytorch" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jingyaogong/minimind-3o-pytorch", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "jingyaogong/minimind-3o-pytorch" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jingyaogong/minimind-3o-pytorch", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jingyaogong/minimind-3o-pytorch with Docker Model Runner:
docker model run hf.co/jingyaogong/minimind-3o-pytorch
Upload 5 files
Browse files- llm_768.pth +3 -0
- llm_768_moe.pth +3 -0
- sft_omni_768.pth +3 -0
- sft_omni_768_moe.pth +3 -0
- sft_zero_768.pth +3 -0
llm_768.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b8c49f6c9d965092e651cafeeaeb8705558632b3fd4ac8ab319cbc5a3cbc4a0
|
| 3 |
+
size 137683346
|
llm_768_moe.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a050020ea6d1b9e824693d0db525b1a0a8b40f36a934ea8d89da161368f20cc1
|
| 3 |
+
size 406719725
|
sft_omni_768.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a05a617858453aa9490bb0ca9e22503e51dd8718348bc06d3a549ffecb589f8
|
| 3 |
+
size 236155558
|
sft_omni_768_moe.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cef510dab06320b1e3991c2bec5ddf2263d1b0c89d1fa4070b2567e4fef6d1a
|
| 3 |
+
size 639710162
|
sft_zero_768.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ee1816a1a37e8165718e4d0a20e9275844f643963899568780ec1941af2e8ab
|
| 3 |
+
size 236155558
|